Upload folder using huggingface_hub

README.md

@@ -0,0 +1,29 @@
+---
+tags:
+- SuperMarioBros-v0
+- RND
+- CNN
+- reinforcement-learning
+- custom-implementation
+- atari
+- MontezumaRevengeNoFrameskip-v4
+model-index:
+- name: RND-SuperMarioBros-v0
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: SuperMarioBros-v0
+      type: SuperMarioBros-v0
+    metrics:
+    - type: mean_reward
+      value: 1998.70 +/- 315.66
+      name: mean_reward
+      verified: false
+---
+
+  # **RND with CNN** Agent playing **SuperMarioBros-v0**
+  This is a trained model of a **RND-CNN** agent playing **SuperMarioBros-v0** .
+  To learn to use this model and train yours check this notebook on kaggle: https://www.kaggle.com/code/syedjarullahhisham/drl-extra-personal-unit-5-rnd-montezuma-mario-bros
+  

agent.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ddf058a32db98bee9716c416a6af9c7c90a8edb11e1a09c1f10cc3e51d0554
+size 21167174

hyperparameters.json

@@ -0,0 +1 @@
+{"trainmethod": "RND", "envid": "SuperMarioBros-v0", "maxstepperepisode": 18000, "learningrate": 0.0001, "numenv": 128, "numstep": 128, "gamma": 0.999, "intgamma": 0.99, "lambda": 0.95, "usegae": true, "clipgradnorm": 0.5, "entropy": 0.001, "epoch": 4, "minibatch": 4, "ppoeps": 0.1, "extcoef": 5.0, "intcoef": 1.0, "stickyaction": true, "actionprob": 0.25, "lifedone": false, "obsnormstep": 50}

results.json

@@ -0,0 +1 @@
+{"env_id": "SuperMarioBros-v0", "mean_reward": 1998.7, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-03T21:57:06.394678"}